Generalization Performance of Multi-pass Stochastic Gradient Descent with Convex Loss Functions.
Stochastic Proximal Methods for Non-Smooth Non-Convex Constrained Sparse Optimization.
Thompson Sampling Algorithms for Cascading Bandits.
Homogeneity Structure Learning in Large-scale Panel Data with Heavy-tailed Errors.
Non-linear, Sparse Dimensionality Reduction via Path Lasso Penalized Autoencoders.
LocalGAN: Modeling Local Distributions for Adversarial Response Generation.
Model Linkage Selection for Cooperative Learning.
Pathwise Conditioning of Gaussian Processes.
Bifurcation Spiking Neural Network.
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks.
Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates.
A Greedy Algorithm for Quantizing Neural Networks.
Neighborhood Structure Assisted Non-negative Matrix Factorization and Its Application in Unsupervised Point-wise Anomaly Detection.
MushroomRL: Simplifying Reinforcement Learning Research.
Locally Differentially-Private Randomized Response for Discrete Distribution Learning.
When random initializations help: a study of variational inference for community detection.
Consensus-Based Optimization on the Sphere: Convergence to Global Minimizers and Machine Learning.
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning.
Bandit Convex Optimization in Non-stationary Environments.
Sparse Convex Optimization via Adaptively Regularized Hard Thresholding.
Testing Conditional Independence via Quantile Regression Based Partial Copulas.
A Lyapunov Analysis of Accelerated Methods in Optimization.
Further results on latent discourse models and word embeddings.
Langevin Dynamics for Adaptive Inverse Reinforcement Learning of Stochastic Gradient Algorithms.
Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning.
Banach Space Representer Theorems for Neural Networks and Ridge Splines.
Empirical Bayes Matrix Factorization.
Approximate Newton Methods.
The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks.
A Unified Convergence Analysis for Shuffling-Type Gradient Methods.
A General Framework for Adversarial Label Learning.
Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples.
Explaining by Removing: A Unified Framework for Model Explanation.
Prediction Under Latent Factor Regression: Adaptive PCR, Interpolating Predictors and Beyond.
Sparse and Smooth Signal Estimation: Convexification of L0-Formulations.
Nonparametric Continuous Sensor Registration.
Guided Visual Exploration of Relations in Data Sets.
ChainerRL: A Deep Reinforcement Learning Library.
Learning Laplacian Matrix from Graph Signals with Sparse Spectral Representation.
Generalization Properties of hyper-RKHS and its Applications.
Consistency of Gaussian Process Regression in Metric Spaces.
FLAME: A Fast Large-scale Almost Matching Exactly Approach to Causal Inference.
Expanding Boundaries of Gap Safe Screening.
Refined approachability algorithms and application to regret minimization with global costs.
Is SGD a Bayesian sampler? Well, almost.
Cooperative SGD: A Unified Framework for the Design and Analysis of Local-Update SGD Algorithms.
Partial Policy Iteration for L1-Robust Markov Decision Processes.
Kernel Smoothing, Mean Shift, and Their Learning Theory with Directional Data.
Bayesian Distance Clustering.
Double Generative Adversarial Networks for Conditional Independence Testing.
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm.
Soft Tensor Regression.
Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be.
DIG: A Turnkey Library for Diving into Graph Deep Learning Research.
A Two-Level Decomposition Framework Exploiting First and Second Order Information for SVM Training Problems.
PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddings.
mlr3pipelines - Flexible Machine Learning Pipelines in R.
Learning Bayesian Networks from Ordinal Data.
A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning.
Failures of Model-dependent Generalization Bounds for Least-norm Interpolation.
Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness.
Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals.
Estimating the Lasso's Effective Noise.
Stochastic Online Optimization using Kalman Recursion.
Tractable Approximate Gaussian Inference for Bayesian Neural Networks.
Interpretable Deep Generative Recommendation Models.
Non-parametric Quantile Regression via the K-NN Fused Lasso.
Projection-free Decentralized Online Learning for Submodular Maximization over Time-Varying Networks.
Global and Quadratic Convergence of Newton Hard-Thresholding Pursuit.
Are We Forgetting about Compositional Optimisers in Bayesian Optimisation?
Analyzing the discrepancy principle for kernelized spectral filter learning algorithms.
Entangled Kernels - Beyond Separability.
Explaining Explanations: Axiomatic Feature Interactions for Deep Networks.
Contrastive Estimation Reveals Topic Posterior Information to Linear Models.
Histogram Transform Ensembles for Large-scale Regression.
COKE: Communication-Censored Decentralized Kernel Learning.
Gradient Methods Never Overfit On Separable Data.
As You Like It: Localization via Paired Comparisons.
A Theory of the Risk for Optimization with Relaxation and its Application to Support Vector Machines.
A General Framework for Empirical Bayes Estimation in Discrete Linear Exponential Family.
On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes.
Wasserstein barycenters can be computed in polynomial time in fixed dimension.
mvlearn: Multiview Machine Learning in Python.
First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems.
Hardness of Identity Testing for Restricted Boltzmann Machines and Potts models.
Shape-Enforcing Operators for Generic Point and Interval Estimators of Functions.
A Unified Sample Selection Framework for Output Noise Filtering: An Error-Bound Perspective.
Individual Fairness in Hindsight.
Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis.
Benchmarking Unsupervised Object Representations for Video Sequences.
dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python.
Adaptive estimation of nonparametric functionals.
On lp-hyperparameter Learning via Bilevel Nonsmooth Optimization.
Learning Sparse Classifiers: Continuous and Mixed Integer Optimization Perspectives.
Learning with semi-definite programming: statistical bounds based on fixed point analysis and excess risk curvature.
An Inertial Newton Algorithm for Deep Learning.
Doubly infinite residual neural networks: a diffusion process approach.
Estimation and Inference for High Dimensional Generalized Linear Models: A Splitting and Smoothing Approach.
Residual Energy-Based Models for Text.
Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory.
Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation.
Multi-class Gaussian Process Classification with Noisy Inputs.
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift.
Alibi Explain: Algorithms for Explaining Machine Learning Models.
Wasserstein distance estimates for the distributions of numerical approximations to ergodic stochastic differential equations.
Exact Asymptotics for Linear Quadratic Adaptive Control.
Oblivious Data for Fairness with Kernels.
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks.
Estimation and Optimization of Composite Outcomes.
Universal consistency and rates of convergence of multiclass prototype algorithms in metric spaces.
Locally Private k-Means Clustering.
Single and Multiple Change-Point Detection with Differential Privacy.
Pseudo-Marginal Hamiltonian Monte Carlo.
Information criteria for non-normalized models.
An Importance Weighted Feature Selection Stability Measure.
Determining the Number of Communities in Degree-corrected Stochastic Block Models.
Subspace Clustering through Sub-Clusters.
A Distributed Method for Fitting Laplacian Regularized Stratified Models.
V-statistics and Variance Estimation.
sklvq: Scikit Learning Vector Quantization.
Batch greedy maximization of non-submodular functions: Guarantees and applications to experimental design.
Consistent estimation of small masses in feature sampling.
Nonparametric Modeling of Higher-Order Interactions via Hypergraphons.
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads.
ROOTS: Object-Centric Representation and Rendering of 3D Scenes.
Linear Bandits on Uniformly Convex Sets.
Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks.
Structure Learning of Undirected Graphical Models for Count Data.
On Solving Probabilistic Linear Diophantine Equations.
On efficient multilevel Clustering via Wasserstein distances.
One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them.
Optimal Rates of Distributed Regression with Imperfect Kernels.
Replica Exchange for Non-Convex Optimization.
LDLE: Low Distortion Local Eigenmaps.
A Contextual Bandit Bake-off.
Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent.
Optimal Bounds between f-Divergences and Integral Probability Metrics.
Mode-wise Tensor Decompositions: Multi-dimensional Generalizations of CUR Decompositions.
Regularized spectral methods for clustering signed networks.
Regulating Greed Over Time in Multi-Armed Bandits.
Bayesian time-aligned factor analysis of paired multivariate time series.
A general linear-time inference method for Gaussian Processes on one dimension.
Learning partial correlation graphs and graphical models by covariance queries.
LassoNet: A Neural Network with Feature Sparsity.
On the Optimality of Kernel-Embedding Based Goodness-of-Fit Tests.
Some Theoretical Insights into Wasserstein GANs.
Statistical Query Lower Bounds for Tensor PCA.
Counterfactual Mean Embeddings.
Hamilton-Jacobi Deep Q-Learning for Deterministic Continuous-Time Systems with Lipschitz Continuous Controls.
Learning a High-dimensional Linear Structural Equation Model via l1-Regularized Regression.
Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMap, and PaCMAP for Data Visualization.
Black-Box Reductions for Zeroth-Order Gradient Algorithms to Achieve Lower Query Complexity.
Prediction against a limited adversary.
Sparse Popularity Adjusted Stochastic Block Model.
The Decoupled Extended Kalman Filter for Dynamic Exponential-Family Factorization Models.
GemBag: Group Estimation of Multiple Bayesian Graphical Models.
Learning interaction kernels in heterogeneous systems of agents from multiple trajectories.
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization.
Optimal Feedback Law Recovery by Gradient-Augmented Sparse Polynomial Regression.
Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs.
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning.
Quasi-Monte Carlo Quasi-Newton in Variational Bayes.
Aggregated Hold-Out.
Collusion Detection and Ground Truth Inference in Crowdsourcing for Labeling Tasks.
Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning.
Kernel Operations on the GPU, with Autodiff, without Memory Overflows.
A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints.
Pykg2vec: A Python Library for Knowledge Graph Embedding.
Risk-Averse Learning by Temporal Difference Methods with Markov Risk Measures.
Safe Policy Iteration: A Monotonically Improving Approximate Policy Iteration Approach.
Integrated Principal Components Analysis.
Optimal Minimax Variable Selection for Large-Scale Matrix Linear Regression Model.
When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks?
Geometric structure of graph Laplacian embeddings.
Unlinked Monotone Regression.
Stable-Baselines3: Reliable Reinforcement Learning Implementations.
An Online Sequential Test for Qualitative Treatment Effects.
On Universal Approximation and Error Bounds for Fourier Neural Operators.
A Unified Framework for Random Forest Prediction Error Estimation.
Learning Whenever Learning is Possible: Universal Learning under General Stochastic Processes.
Optimization with Momentum: Dynamical, Control-Theoretic, and Symplectic Perspectives.
Integrative Generalized Convex Clustering Optimization and Feature Selection for Mixed Multi-View Data.
Particle-Gibbs Sampling for Bayesian Feature Allocation Models.
On ADMM in Deep Learning: Convergence and Saturation-Avoidance.
Tighter Risk Certificates for Neural Networks.
Ranking and synchronization from pairwise measurements via SVD.
Conditional independences and causal relations implied by sets of equations.
OpenML-Python: an extensible Python API for OpenML.
Consistent Semi-Supervised Graph Regularization for High Dimensional Data.
From Low Probability to High Confidence in Stochastic Convex Optimization.
Transferability of Spectral Graph Convolutional Neural Networks.
Langevin Monte Carlo: random coordinate descent and variance reduction.
The ensmallen library for flexible numerical optimization.
Statistical Guarantees for Local Spectral Clustering on Random Neighborhood Graphs.
Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo.
A Unified Framework for Spectral Clustering in Sparse Graphs.
PeerReview4All: Fair and Accurate Reviewer Assignment in Peer Review.
Classification vs regression in overparameterized regimes: Does the loss function matter?
FATE: An Industrial Grade Platform for Collaborative Learning With Data Protection.
Statistically and Computationally Efficient Change Point Localization in Regression Settings.
DeEPCA: Decentralized Exact PCA with Linear Convergence Rate.
A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms.
Reproducing kernel Hilbert C*-module and kernel mean embeddings.
Optimized Score Transformation for Consistent Fair Classification.
A flexible model-free prediction-based framework for feature ranking.
An algorithmic view of L2 regularization and some path-following algorithms.
Implicit Langevin Algorithms for Sampling From Log-concave Densities.
GIBBON: General-purpose Information-Based Bayesian Optimisation.
Normalizing Flows for Probabilistic Modeling and Inference.
Beyond English-Centric Multilingual Machine Translation.
Statistical guarantees for local graph clustering.
Communication-Efficient Distributed Covariance Sketch, with Application to Distributed PCA.
River: machine learning for streaming data in Python.
L-SVRG and L-Katyusha with Arbitrary Sampling.
NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation.
On Multi-Armed Bandit Designs for Dose-Finding Trials.
Matrix Product States for Inference in Discrete Probabilistic Models.
Context-dependent Networks in Multivariate Time Series: Models, Methods, and Risk Bounds in High Dimensions.
Simultaneous Change Point Inference and Structure Recovery for High Dimensional Gaussian Graphical Models.
Convex Clustering: Model, Theoretical Guarantee and Efficient Algorithm.
Learning Strategies in Decentralized Matching Markets under Uncertain Preferences.
Estimating Uncertainty Intervals from Collaborating Networks.
On the Hardness of Robust Classification.
Probabilistic Iterative Methods for Linear Systems.
Hybrid Predictive Models: When an Interpretable Model Collaborates with a Black-box Model.
POT: Python Optimal Transport.
Bayesian Text Classification and Summarization via A Class-Specified Topic Model.
Bandit Learning in Decentralized Matching Markets.
Achieving Fairness in the Stochastic Multi-Armed Bandit Problem.
Predictive Learning on Hidden Tree-Structured Ising Models.
Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference.
Inference for Multiple Heterogeneous Networks with a Common Invariant Subspace.
Improved Shrinkage Prediction under a Spiked Covariance Structure.
Phase Diagram for Two-layer ReLU Neural Networks at Infinite-width Limit.
Analysis of high-dimensional Continuous Time Markov Chains using the Local Bouncy Particle Sampler.
CAT: Compression-Aware Training for bandwidth reduction.
Finite Time LTI System Identification.
A Bayes-Optimal View on Adversarial Examples.
Flexible Signal Denoising via Flexible Empirical Bayes Shrinkage.
Gaussian Approximation for Bias Reduction in Q-Learning.
An Empirical Study of Bayesian Optimization: Acquisition Versus Partition.
Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits.
Asymptotic Normality, Concentration, and Coverage of Generalized Posteriors.
giotto-tda: : A Topological Data Analysis Toolkit for Machine Learning and Data Exploration.
Domain adaptation under structural causal models.
How Well Generative Adversarial Networks Learn Distributions.
Limit theorems for out-of-sample extensions of the adjacency and Laplacian spectral embeddings.
On the Estimation of Network Complexity: Dimension of Graphons.
Knowing what You Know: valid and validated confidence sets in multiclass and multilabel prediction.
Incorporating Unlabeled Data into Distributionally Robust Learning.
Inference In High-dimensional Single-Index Models Under Symmetric Designs.
Path Length Bounds for Gradient Descent and Flow.
A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Families.
Differentially Private Regression and Classification with Sparse Gaussian Processes.
Multilevel Monte Carlo Variational Inference.
RaSE: Random Subspace Ensemble Classification.
Continuous Time Analysis of Momentum Methods.
Unfolding-Model-Based Visualization: Theory, Method and Applications.
Asynchronous Online Testing of Multiple Hypotheses.
Preference-based Online Learning with Dueling Bandits: A Survey.
A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration.
Fast Learning for Renewal Optimization in Online Task Scheduling.
Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime.
Adversarial Monte Carlo Meta-Learning of Optimal Prediction Procedures.
Improving Reproducibility in Machine Learning Research(A Report from the NeurIPS 2019 Reproducibility Program).
Strong Consistency, Graph Laplacians, and the Stochastic Block Model.
Online stochastic gradient descent on non-convex losses from high-dimensional inference.
Domain Generalization by Marginal Transfer Learning.
Stochastic Proximal AUC Maximization.
On the Riemannian Search for Eigenvector Computation.
Hoeffding's Inequality for General Markov Chains and Its Applications to Statistical Learning.
Attention is Turing-Complete.
A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenters.
Hyperparameter Optimization via Sequential Uniform Designs.
Graph Matching with Partially-Correct Seeds.
Sparse Tensor Additive Regression.
Factorization Machines with Regularization for Sparse Feature Interactions.
How to Gain on Power: Novel Conditional Independence Tests Based on Short Expansion of Conditional Mutual Information.
Integrative High Dimensional Multiple Testing with Heterogeneity under Data Sharing Constraints.
Edge Sampling Using Local Network Information.
Mixing Time of Metropolis-Hastings for Bayesian Community Detection.
From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction.
Method of Contraction-Expansion (MOCE) for Simultaneous Inference in Linear Models.
Convex Geometry and Duality of Over-parameterized Neural Networks.
Inference for the Case Probability in High-dimensional Logistic Regression.
Representer Theorems in Banach Spaces: Minimum Norm Interpolation, Regularized Learning and Semi-Discrete Inverse Problems.
What Causes the Test Error? Going Beyond Bias-Variance via ANOVA.
Dynamic Tensor Recommender Systems.
Towards a Unified Analysis of Random Fourier Features.
A Bayesian Contiguous Partitioning Method for Learning Clustered Latent Variables.
